arch/x86/Makefile disables SSE and SSE2 for the whole kernel. The
AMDGPU drivers modified in this patch re-enable SSE but not SSE2. Turn
on SSE2 to support emitting double precision floating point instructions
rather than calls to non-existent (usually available from gcc_s or
compiler_rt) floating point helper routines for Clang.
This was originally landed in:
commit
10117450735c ("drm/amd/display: add -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines")
but reverted in:
commit
193392ed9f69 ("Revert "drm/amd/display: add -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines"")
due to bugreports from GCC builds. Add guards to only do so for Clang.
Link: https://bugs.freedesktop.org/show_bug.cgi?id=109487
Link: https://github.com/ClangBuiltLinux/linux/issues/327
Suggested-by: Sedat Dilek <[email protected]>
Suggested-by: Sami Tolvanen <[email protected]>
Signed-off-by: Nick Desaulniers <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
calcs_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_CLANG
+calcs_ccflags += -msse2
+endif
+
CFLAGS_dcn_calcs.o := $(calcs_ccflags)
CFLAGS_dcn_calc_auto.o := $(calcs_ccflags)
CFLAGS_dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare
CFLAGS_dcn20_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_CLANG
+CFLAGS_dcn20_resource.o += -msse2
+endif
+
AMD_DAL_DCN20 = $(addprefix $(AMDDALPATH)/dc/dcn20/,$(DCN20))
AMD_DISPLAY_FILES += $(AMD_DAL_DCN20)
dml_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_CLANG
+dml_ccflags += -msse2
+endif
+
CFLAGS_display_mode_lib.o := $(dml_ccflags)
ifdef CONFIG_DRM_AMD_DC_DCN2_0
dsc_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_CLANG
+dsc_ccflags += -msse2
+endif
+
CFLAGS_rc_calc.o := $(dsc_ccflags)
CFLAGS_rc_calc_dpi.o := $(dsc_ccflags)
CFLAGS_codec_main_amd.o := $(dsc_ccflags)